www.cmm.bristol.ac.uk/forum

I am attempting to assess the variance explained by each level of an outcome. When I run the binomial model below, it does not provide the estimate at level 1, only levels 2 and 3. What additional steps must I take to get level 1 variance (estimate)?

EX: runmlwin OUTCOME cons, level3(LEVEL: cons) level2(LEVEL: cons) level1(LEVEL:) discrete(distribution(binomial) link(logit) denominator(cons) pql2) nopause

MLwiN does not estimate a level-1 variance for binomial models, instead constraining it to a fixed value. For more details see:

Apportioning Variation in Multilevel Models

and

Partitioning variation across levels